INDEX

Explanations

references to features and their attributes in technology-related contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

"feature"

np_acts-logits-general · gemini-2.0-flash

features, selection, extensions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

idp

-0.59

atorias

-0.57

İstinadlar

-0.57

 Abbé

-0.57

PVA

-0.57

 dõi

-0.56

AccessFile

-0.56

uegos

-0.56

missions

-0.56

 obicei

-0.55

POSITIVE LOGITS

 prominently

1.09

 features

0.84

 Features

0.76

features

0.74

Features

0.71

 FEATURES

0.69

 feature

0.67

 FEATURE

0.66

mybatisplus

0.65

 UnityEditor

0.64

Activations Density 0.101%

references to features and their attributes in technology-related contexts

"feature"

features, selection, extensions

No Comments

No Known Activations